|
The journal Automotive Innovation is sponsored by China SAE,
published through Springer, distributed around the world, and
reflects the top-level research and technical advance of
automotive engineering. Automotive Innovation newsletter in December includes the following contents： 1. Article Recommendation——Three papers on Autonomous Driving Safety 2. China SAE News:
·Automotive Innovation Ranks Q1 in
the World Journal Clout Index |
  
|
Towards Safe Autonomous Driving: Decision Making with
Observation-Robust Reinforcement Learning Xiangkun He, Chen Lv |
||
| Most real-world situations involve unavoidable measurement noises or perception errors which result in unsafe decision making or even casualty in autonomous driving. To address these issues and further improve safety, automated driving is required to be capable of handling perception uncertainties. Here, this paper presents an observation-robust reinforcement learning against observational uncertainties to realize safe decision making for autonomous vehicles. Specifically, an adversarial agent is trained online to generate optimal adversarial attacks on observations, which attempts to amplify the average variation distance on perturbed policies. In addition, an observation-robust actor-critic approach is developed to enable the agent to learn the optimal policies and ensure that the changes of the policies perturbed by optimal adversarial attacks remain within a certain bound. Lastly, the safe decision making scheme is evaluated on a lane change task under complex highway traffic scenarios. The results show that the developed approach can ensure autonomous driving performance, as well as the policy robustness against adversarial attacks on observations. | |||
|
Keywords: Autonomous vehicle, Robust reinforcement learning,
Safe decision making, Adversarial attack He, X., Lv, C.: Towards safe autonomous driving: decision making with observation-robust reinforcement learning. Automot. Innov. 6, 509–520 (2023) |
|||
| Full Paper Reading>> | |||
|
European Research Project’s Contributions to a Safer
Automated Road Traffic
Felix Fahrenkrog, Susanne Reithinger, Burak Gülsen, Florian Raisch |
||
| Automated driving is poised to become a pivotal technology in the future automotive transportation. However, it is evident that the implementation of automated driving presents significant technical challenges. To accelerate the development and deployment of automated driving the European Commission initiated the research project L3Pilot in 2017. With a budget of 65 million Euros and the involvement of 13 car manufacturers, L3Pilot stands as the largest European project on automated driving (AD). This paper serves as a comprehensive account of BMW’s main activities in the L3Pilot project that ended in 2021. The research questions addressed in this project are related to the following topics: what are the guidelines for the development of AD? How do potential customers interact with AD? And what is the safety impact assessment of AD? The paper presents the findings related to all three research questions to contribute to the further development of automated driving. For this purpose together with other partners the Code of Practice of AD was defined as a guideline for the development of future AD systems. Related to the second question, BMW conducted tests with AD systems on motorways and in parking scenarios, with over 100 test subjects experiencing AD. The studies provide input and considerations for future AD systems. Finally, in the safety impact assessment, BMW investigated with other project partners the potential safety benefits of AD through simulation. The results show a potential to improve road safety. In conclusion, the exploration of all three research questions has led to a deeper understanding of SAE Level 3 AD. | |||
|
Keywords: Automated driving, L3Pilot, Code of Practice, Pilot,
Safety impact assessment, User acceptance
Fahrenkrog, F., Reithinger, S., Gülsen, B. et al.: European research project’s contributions to a safer automated road traffic. Automot. Innov. 6, 521–530 (2023) |
|||
| Full Paper Reading>> | |||
|
Genetic Algorithm-Based SOTIF Scenario Construction for
Complex Traffic Flow
Shulian Zhao, Jianli Duan, Siyu Wu, Xinyu Gu, Chuzhao Li, Kai Yin, Hong Wang |
||
| The Safety of The Intended Functionality (SOTIF) challenge represents the triggering condition by elements of a specific scenario and exposes the function limitation of an autonomous vehicle (AV), which leads to hazards. As for operation-content-related features, the scenario is similar to AVs’ SOTIF research and development. Therefore, scenario generation is a significant topic for SOTIF verification and validation procedure, especially in the simulation testing of AVs. Thus, in this paper, a well-designed scenario architecture is first defined, with comprehensive scenario elements, to present SOTIF trigger conditions. Then, considering complex traffic disturbance as trigger conditions, a novel SOTIF scenario generation method is developed. An indicator, also known as Scenario Potential Risk, is defined as the combination of the safety control intensity and the prior collision probability. This indicator helps identify critical scenarios in the proposed method. In addition, the corresponding vehicle motion models are established for general straight roads, curved roads, and safety assessment areas. As for the traffic participants’ motion model, it is designed to construct the key dynamic events. To efficiently search for critical scenarios with the trigger of complex traffic flow, this scenario is encoded as genes and it is regenerated through selection, mutation, and crossover iteration processes, known as the Genetic Algorithm (GA). Experimental results show that the GA-based method could efficiently construct diverse and critical traffic scenarios, contributing to the construction of the SOTIF scenario library. | |||
|
Keywords: SOTIF triggers conditions, Scenario generation,
Genetic algorithm, Complex traffic disturbance Liu, X., Wang, M., Cao, R. et al.: Review of abnormality detection and fault diagnosis methods for lithium-ion batteries. Automot. Innov. 6(2), 256–267 (2023) |
|||
| Full Paper Reading>> | |||
| ISC 2023 to be held on 10-12 July 2023 in Chongqing | |||
 The 2023 edition of "World Journal Clout Index (WJCI) of Scientific and Technological Periodicals" report was released recently. Automotive Innovation ranks Q1 in the discipline of "Automobile, Locomotive and Vehicle Engineering". WJCI report, based on the R&D investment, research paper output, number of researchers, and the publication scale of journals, determines the rank and selection of source journals. It selects the most excellent journals with the most representative regions, disciplines and industries from more than 60,000 academic journals around the world. For more information, please click here . |
|||
| The 2023 World New Energy Vehicle Congress was Successfully Held | |||
 On 7 December, the 2023 World New Energy Vehicle Congress opened in Haikou, Hainan. More than 1,000 representatives attended the congress, covering 23 countries and regions. Providing both online livestream and physical gathering, the congress discussed topics such as "green low-carbon development strategy" and "accelerating the reconstruction of the new ecology of the automotive industry". The Consensus of 2023 World New Energy Vehicle Congress and the results of "2023 Global New Energy Vehicle Frontier and Innovative Technologies" were released. For more detailed information about the congress,click here . |
|||
| CSAE Young Scientist Seminar on New Energy Vehicle Thermal Management Technology was Successfully Held | |||
 On 16th December, " CSAE Young Scientist Seminar on New Energy Vehicle Thermal Management Technology" was successfully held at BYD Engineering Research Institute in Shenzhen, China. A total of 11 academic experts and 19 technical experts attended the meeting. The attendees discussed thermal management technology of new energy vehicles. The seminar seeks to address critical thermal management technology challenges, such as energy management and comprehensive utilization of vehicle thermal management, integration of vehicle thermal management components, and active and passive energy-efficient cabin heating technology. For more information, please click here . |
|||
| Automotive Innovation launched Directory of AUIN Published Papers | |||
 Automotive Innovation launched the Directory of AUIN Published Papers. It offers access to locate all papers published on Automotive Innovation. All articles published in the journal during 2022 – 2023 are listed according to the technical field. Please click here to download the file. |
|||
|
Automotive Innovation Sponsored by China SAE and published globally via Springer Nature, Automotive Innovation aims to be a world-class journal that provides abundant sources of innovative findings for automotive engineers and scientists. The journal is published quarterly, ensuring high-quality papers satisfying international standards. With the editorial board consisting of world-renowned experts, it has attracted readers from 72 countries and regions. The highest download of a single article wins more than 32,000. The journal is indexed in Ei Compendex, ESCI, and Scopus (IF2022=6.1). The journal provides a forum for the research of principles, methodologies, designs, theoretical background, and cutting-edge technologies in connection with the development of vehicle and mobility. The main topics cover: energy-saving, electrification, intelligent and connected, safety, and emerging vehicle technologies. Editors-in-Chief Jun Li, Academician of CAE, President of China SAE, Professor of Tsinghua University Frank Zhao, Honorary Lifetime President of FISITA, Director of Tsinghua Automotive Strategy Research Institute, Professor of Tsinghua University Honorary and Founding Executive Editor-in-Chief Prof. Fangwu (Mike) Ma Executive Associate Editor-in-Chief Prof. Xinjie Zhang, Professor of Jilin University |
||||
|
Paper submission and browse
www.ChinaSAEJournal.com.cn www.springer.com/42154 Contacts: Ms. Lily Lu Tel: +86-10-50950101 Email: jai@sae-china.org 
|
|
|||
Sponsored by
|
Published by
|
|||